chore: Update the reference in readme (#6298)

Signed-off-by: pvijayakrish <pvijayakrish@nvidia.com>

deploy/helm/charts/platform/components/operator/crds/nvidia.com_dynamographdeploymentrequests.yaml

@@ -130,7 +130,7 @@ spec:
                         WorkersImage specifies the container image to use for DynamoGraphDeployment worker components.
                         This image is used for both temporary DGDs created during online profiling and the final DGD.
                         If omitted, the image from the base config file (e.g., disagg.yaml) is used.
-                        Example: "nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.6.1"
+                        Example: "nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.9.0"
                       type: string
                   type: object
                 enableGpuDiscovery:
@@ -205,7 +205,7 @@ spec:
                       description: |-
                         ProfilerImage specifies the container image to use for profiling jobs.
                         This image contains the profiler code and dependencies needed for SLA-based profiling.
-                        Example: "nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.6.1"
+                        Example: "nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.9.0"
                       type: string
                     resources:
                       description: |-

deploy/operator/api/v1alpha1/dynamographdeploymentrequest_types.go

@@ -64,7 +64,7 @@ type ProfilingConfigSpec struct {
 
 	// ProfilerImage specifies the container image to use for profiling jobs.
 	// This image contains the profiler code and dependencies needed for SLA-based profiling.
-	// Example: "nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.6.1"
+	// Example: "nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.9.0"
 	// +kubebuilder:validation:Required
 	ProfilerImage string `json:"profilerImage"`
 
@@ -132,7 +132,7 @@ type DeploymentOverridesSpec struct {
 	// WorkersImage specifies the container image to use for DynamoGraphDeployment worker components.
 	// This image is used for both temporary DGDs created during online profiling and the final DGD.
 	// If omitted, the image from the base config file (e.g., disagg.yaml) is used.
-	// Example: "nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.6.1"
+	// Example: "nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.9.0"
 	// +kubebuilder:validation:Optional
 	WorkersImage string `json:"workersImage,omitempty"`
 }

deploy/operator/config/crd/bases/nvidia.com_dynamographdeploymentrequests.yaml

@@ -130,7 +130,7 @@ spec:
                         WorkersImage specifies the container image to use for DynamoGraphDeployment worker components.
                         This image is used for both temporary DGDs created during online profiling and the final DGD.
                         If omitted, the image from the base config file (e.g., disagg.yaml) is used.
-                        Example: "nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.6.1"
+                        Example: "nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.9.0"
                       type: string
                   type: object
                 enableGpuDiscovery:
@@ -205,7 +205,7 @@ spec:
                       description: |-
                         ProfilerImage specifies the container image to use for profiling jobs.
                         This image contains the profiler code and dependencies needed for SLA-based profiling.
-                        Example: "nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.6.1"
+                        Example: "nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.9.0"
                       type: string
                     resources:
                       description: |-

deploy/operator/config/samples/nvidia.com_v1alpha1_dynamographdeploymentrequest.yaml

@@ -25,7 +25,7 @@ spec:
   backend: trtllm
 
   # ProfilerImage is the container image to use for profiling jobs (required)
-  profilerImage: "nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:0.6.1"
+  profilerImage: "nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:0.9.0"
 
   # ProfilingConfig maps directly to the profile_sla.py config format
   # See dynamo/profiler/utils/profiler_argparse.py for complete schema

docs/pages/kubernetes/api-reference.md

@@ -176,7 +176,7 @@ _Appears in:_
 | `namespace` _string_ | Namespace is the desired namespace for the created DynamoGraphDeployment.<br />If not specified, defaults to the DGDR namespace. |  | Optional: \{\} <br /> |
 | `labels` _object (keys:string, values:string)_ | Labels are additional labels to add to the DynamoGraphDeployment metadata.<br />These are merged with auto-generated labels from the profiling process. |  | Optional: \{\} <br /> |
 | `annotations` _object (keys:string, values:string)_ | Annotations are additional annotations to add to the DynamoGraphDeployment metadata. |  | Optional: \{\} <br /> |
-| `workersImage` _string_ | WorkersImage specifies the container image to use for DynamoGraphDeployment worker components.<br />This image is used for both temporary DGDs created during online profiling and the final DGD.<br />If omitted, the image from the base config file (e.g., disagg.yaml) is used.<br />Example: "nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.6.1" |  | Optional: \{\} <br /> |
+| `workersImage` _string_ | WorkersImage specifies the container image to use for DynamoGraphDeployment worker components.<br />This image is used for both temporary DGDs created during online profiling and the final DGD.<br />If omitted, the image from the base config file (e.g., disagg.yaml) is used.<br />Example: "nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.9.0" |  | Optional: \{\} <br /> |
 
 
 #### DeploymentStatus
@@ -921,7 +921,7 @@ _Appears in:_
 | --- | --- | --- | --- |
 | `config` _[JSON](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.28/#json-v1-apiextensions-k8s-io)_ | Config is the profiling configuration as arbitrary JSON/YAML. This will be passed directly to the profiler.<br />The profiler will validate the configuration and report any errors. |  | Optional: \{\} <br />Type: object <br /> |
 | `configMapRef` _[ConfigMapKeySelector](#configmapkeyselector)_ | ConfigMapRef is an optional reference to a ConfigMap containing the DynamoGraphDeployment<br />base config file (disagg.yaml). This is separate from the profiling config above.<br />The path to this config will be set as engine.config in the profiling config. |  | Optional: \{\} <br /> |
-| `profilerImage` _string_ | ProfilerImage specifies the container image to use for profiling jobs.<br />This image contains the profiler code and dependencies needed for SLA-based profiling.<br />Example: "nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.6.1" |  | Required: \{\} <br /> |
+| `profilerImage` _string_ | ProfilerImage specifies the container image to use for profiling jobs.<br />This image contains the profiler code and dependencies needed for SLA-based profiling.<br />Example: "nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.9.0" |  | Required: \{\} <br /> |
 | `outputPVC` _string_ | OutputPVC is an optional PersistentVolumeClaim name for storing profiling output.<br />If specified, all profiling artifacts (logs, plots, configs, raw data) will be written<br />to this PVC instead of an ephemeral emptyDir volume. This allows users to access<br />complete profiling results after the job completes by mounting the PVC.<br />The PVC must exist in the same namespace as the DGDR.<br />If not specified, profiling uses emptyDir and only essential data is saved to ConfigMaps.<br />Note: ConfigMaps are still created regardless of this setting for planner integration. |  | Optional: \{\} <br /> |
 | `resources` _[ResourceRequirements](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.28/#resourcerequirements-v1-core)_ | Resources specifies the compute resource requirements for the profiling job container.<br />If not specified, no resource requests or limits are set. |  | Optional: \{\} <br /> |
 | `tolerations` _[Toleration](https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.28/#toleration-v1-core) array_ | Tolerations allows the profiling job to be scheduled on nodes with matching taints.<br />For example, to schedule on GPU nodes, add a toleration for the nvidia.com/gpu taint. |  | Optional: \{\} <br /> |